3-D Vectorization via Inverse Projection and Depth Sorting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for converting raster images to vector graphics struggle to accurately represent high-frequency details and photo-realistic appearances, leading to pixelation or distortion when scaling or zooming, and require computationally expensive re-rendering processes.
Innovation Solution
A 3-D vectorization system that performs an inverse projection of colors onto a 2-D mesh, creating a triangle mesh with subdivided triangles and assigning colors to vertices, allowing for scalable 2-D vector graphics without pixelation or distortion, while preserving edge definition and high-frequency object information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional raster image conversion methods are used, then the conversion process is simple, but the result suffers from pixelation and distortion when scaling
Solution Approach 1:
The patent inverts the traditional rendering pipeline by performing inverse projection from 3D mesh to 2D vector space. Instead of converting raster to vector directly, it projects 3D mesh vertices and colors onto 2D plane, then sorts by depth to create final 2D vector graphic. This inversion enables resolution-independent scaling while maintaining image quality.
Solution Approach 2:
The patent introduces a 3D intermediate representation (triangle mesh with vertices and colors) between the input 3D rendered image and output 2D vector graphic. By working in 3D space with depth information and then projecting to 2D with proper sorting, the system achieves resolution independence and eliminates pixelation issues inherent in direct 2D conversion methods.
2Manufacturing precision
If full triangle mesh processing is performed, then complete color coverage is achieved, but processing time and memory usage increase
Solution Approach 1:
The patent extracts and removes triangles that are not visible from the camera viewpoint by performing depth sorting and discarding z-values of hidden surfaces. This extraction of only visible triangle information reduces processing time and memory usage while maintaining complete color coverage for all visible areas.
Solution Approach 2:
The patent applies different processing treatments to different regions of the mesh based on visibility. Visible triangles receive full color assignment and are retained, while invisible triangles are removed. This local differentiation optimizes processing resources by focusing only on visible portions of the scene.
Data Source
AI summary
Embodiments are disclosed for performing 3-D vectorization. The method includes obtaining a three-dimensional rendered image and a camera position. The method further includes obtaining a triangle mesh representing the three-dimensional rendered image. The method further involves creating a reduced triangle mesh by removing one or more triangles from the triangle mesh. The method further involves subdividing each triangle of the reduced triangle mesh into one or more subdivided triangles. The method further involves performing a mapping of each pixel of the three-dimensional rendered image to the reduced triangle mesh. The method further involves assigning a color value to each vertex of the reduced triangle mesh. The method further involves sorting each triangle of the reduced triangle mesh using a depth value of each triangle. The method further involves generating a two-dimensional triangle mesh using the sorted triangles of the reduced triangle mesh.